SKILLEMALL.ai
GitHub ↗ RU Sign in

BB sports-betting

Place and claim decentralized sports bets on-chain via Pinwin and Azuro: real-time odds, high liquidity, no custody. Fetch prematch and live games from the data-feed, pick a selection, then sign and submit. Use when the user wants to bet on sports with Pinwin, browse games, place a bet, or check or redeem winnings.

modbender/skill-library-mcp Claude Code author: modbender MIT 8 files body ≈ 2 773 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Place and claim decentralized sports bets on-chain via Pinwin and Azuro: real-time odds, high liquidity, no custody.

As a process B 65/100 · Nearly there — weak spots: result and completion, running it twice

ProcedureAI and agentsData and analyticstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
91
Quality 40%
87
Run on models
none yet
Process rating
B
65/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
Failures and branches w 10
50
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Risky intent medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Risky intent intent-wallet-secrets SKILL.md:36
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - **BETTOR_PRIVATE_KEY** — Wallet private key (hex) for signing bets and claim transactions. High-sensitivity; do not log or expose. Required for placing and claiming. Use a dedicated betting wallet w
    • low Secrets in code secret-high-entropy-token references/polygon.md:14
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)
      | **relayer** | `0x8d…a9d` (for USDT approval; verify bet payload does not override) |
      detectortable
    • low Secrets in code secret-high-entropy-token references/polygon.md:16
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | **core** (ClientCore) | `0xF9…AC7` (for bet payload clientData.core; same as claimContract) |
      table
    • low Secrets in code secret-high-entropy-token references/polygon.md:17
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | **claimContract** (ClientCore, redeem won/canceled bets) | `0xF9…AC7` |
      table
    • low Risky intent intent-wallet-secrets SKILL.md:4
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      compatibility: "Requires Node, viem and @azuro-org/dictionaries (for human-readable market/selection names). Required env: BETTOR_PRIVATE_KEY (wallet private key; high-sensitivity). Optional env: POLY
      quoted

    Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 65/100

    • 0Result and completion. Does not say what the result is
    • 30Running it twice. 7 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (web, node) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 31 steps, 2 vague phrases
    • 100When it triggers. States when to use and when not to
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2773 tokens
    • 100Progress reporting. Reports progress
    • low 11 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 316: enough signal without eating the budget
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 31 items
    • +4Has examples (2 code blocks)
    • +4Reference files are cited in the instructions (6 of 6)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.